Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sethdford/claude-skills --skill fitness-function-designgit clone --depth 1 https://github.com/sethdford/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sethdford/claude-skills/fitness-function-design)<a href="https://agentmods.dev/skills/sethdford/claude-skills/fitness-function-design"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/fitness-function-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sethdford/claude-skills/fitness-function-design"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/fitness-function-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00631 |
| Opus 5 | $0.00019 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
fitness-function-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fitness Function Design
Design quantifiable metrics to measure architecture health and automatically enforce quality standards.
Context
You are designing fitness functions to measure architectural quality. Create metrics for coupling, modularity, scalability, performance. Automate checks in CI/CD for continuous feedback.
Domain Context
Based on evolutionary architecture and fitness function research (Thoughtworks):
- Coupling Metrics: Layer violations, cyclic dependencies, test isolation
- Modularity Metrics: Module fan-in/fan-out, cohesion, abstract instability
- Scalability Metrics: Throughput (RPS), latency (p95, p99), resource utilization
- Security Metrics: Secrets in code, dependency vulnerabilities, known security patterns
- Code Quality Metrics: Complexity (cyclomatic), duplication, test coverage
Instructions
-
Identify Key Quality Attributes: What matters most? Scalability? Security? Testability? Maintainability? Pick 3-4.
-
Define Metrics for Each Attribute: Scalability: p99 latency < 200ms, peak RPS capacity. Security: zero secrets in code, all dependencies scanned. Testability: > 80% test coverage, no untestable dependencies.
-
Set Thresholds: Below threshold: pass. Above: fail (blocks merge). Make thresholds achievable but stretch. Too strict: teams bypass. Too loose: no effect.
-
Automate Checks: Integrate into CI/CD. Run on every PR. Parse test coverage reports, dependency scanners, performance benchmarks. Fail PR if fitness functions breach.
-
Monitor and Adjust: Track metrics over time. Are they trending right? Do developers understand why they matter? Adjust thresholds based on feedback and organizational priorities.
Anti-Patterns
- Too Many Fitness Functions: 50 metrics in CI/CD. Result: long builds, false positives, ignored. Guard: 5-10 core metrics max. Automate what matters; remove noise.
- Fitness Functions Without Context: "Cyclomatic complexity > 10 fails". Developer doesn't understand why. Result: frustrated, rules bypassed. Guard: Document rationale; train teams; explain tradeoffs.
- Static Thresholds: Set once, never changed. Organization evolves, thresholds stale. Result: metrics become irrelevant. Guard: Review quarterly; adjust based on trends and priorities.
- Metrics Without Action: Fitness functions fail but no one addresses. Result: technical debt accumulates. Guard: Failed checks require action; track and fix root causes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 48 lines · 38 tokens per session scan A 9c10c4056e9b
fitness-function-design is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 631 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
cmd_flutter_test
Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and integration tests.
cmd_cpp_test
Enforce TDD workflow for C++. Write GoogleTest tests first, then implement. Verify coverage with gcov/lcov.
cmd_e2e
Legacy slash-entry shim for the e2e-testing skill. Prefer the skill directly.
cmd_go_test
Enforce TDD workflow for Go. Write table-driven tests first, then implement. Verify 80%+ coverage with go test -cover.
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.